Bug 2548051 (CVE-2026-107291) - CVE-2026-107291 pydantic-ai: pydantic-ai-slim: Pydantic AI: Information disclosure via incomplete telemetry content redaction
Summary: CVE-2026-107291 pydantic-ai: pydantic-ai-slim: Pydantic AI: Information discl...
Keywords:
Status: NEW
Alias: CVE-2026-107291
Product: Security Response
Classification: Other
Component: vulnerability
Version: unspecified
Hardware: All
OS: Linux
medium
medium
Target Milestone: ---
Assignee: Product Security DevOps Team
QA Contact:
URL:
Whiteboard:
Depends On:
Blocks:
TreeView+ depends on / blocked
 
Reported: 2026-10-08 16:42 UTC by OSIDB Bzimport
Modified: 2026-10-08 16:51 UTC (History)
6 users (show)

Fixed In Version:
Clone Of:
Environment:
Last Closed:
Embargoed:


Attachments (Terms of Use)

Description OSIDB Bzimport 2026-10-08 16:42:38 UTC
Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 0.3.4 until 1.107.6 and 2.44.0, OpenTelemetry instrumentation configured with InstrumentationSettings(include_content=False) can still export sensitive agent content through exception.message and exception.stacktrace events, error status descriptions, and model_request_parameters containing instructions or the prompted_output_template. The exposed data is available to readers of the configured telemetry backend and can include tool feedback, provider error bodies, runtime instructions, and structured-output templates even though message attributes are redacted. This issue does not grant new access to agent data, and deployments that do not use include_content=False are not affected by the setting bypass. This issue is fixed in versions 1.107.6 and 2.44.0.


Note You need to log in before you can comment on or make changes to this bug.